EPFL Researchers Release Spatial Proteomics Image Collection
The new open-access resource, named spora, contains over 13,000 multiplex images from thousands of patients.
Updated on Oct. 28, 2026 in Diseases — General
Live Poll
Should large-scale medical datasets be made open-access to accelerate artificial intelligence development?
Researchers at EPFL, in collaboration with the European Bioinformatics Institute, have launched spora, an open-access spatial proteomics tissue image collection. This resource features 13,546 standardized multiplex images derived from 5,477 patients.
Why it matters
The collection aims to bridge gaps in current scientific research by standardizing images from diverse imaging technologies. By enabling easier cross-study data comparison, the resource is designed to accelerate AI-driven insights into tissue function and disease development.
The spora collection includes 13,546 multiplex images spanning 14 tissue origins and five different imaging technologies. Researchers curated this dataset from 5,477 patients after two years of standardization work.
The players
EPFL
The Swiss Federal Institute of Technology Lausanne is a prominent public research university specializing in natural sciences and engineering.
European Bioinformatics Institute
This intergovernmental research organization provides free access to biological data and focuses on the advancement of bioinformatics and life sciences.
The details
The team organized thousands of images and standardized protein annotations while identifying individual cells to facilitate analysis. Existing spatial proteomics datasets have historically been difficult to integrate due to variations in equipment, target proteins, and data storage formats.
Timeline
Scientists spent two years creating the spora collection from 2024 to 2026.
Health Landscape
This release aligns with the European Bioinformatics Institute's data sharing standards to improve global scientific data interoperability. It marks a shift toward standardized, cross-institutional datasets that move beyond the limitations of siloed laboratory research.
The public availability of this massive dataset allows global researchers to refine AI models that could eventually lead to more accurate disease diagnosis and treatment planning. Patients may benefit long-term from the accelerated development of precision medicine tools enabled by this data.
The takeaway
The spora collection demonstrates how standardizing complex biological data can significantly speed up medical research. Scientists can now utilize this unified resource to investigate tissue development with greater consistency than previously possible.
Further reading
Learn more about the latest research in Diseases — General.
Source note: This article includes information reported by Swiss Federal Institute of Technology, Lausanne (EPFL).
Live Poll
Should large-scale medical datasets be made open-access to accelerate artificial intelligence development?
